DeepSeek R1 0528 (May '25) vs DeepSeek V3.1 (Reasoning)
DeepSeek R1 0528 (May '25) vs DeepSeek V3.1 (Reasoning). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.
Verdict
Comparison incomplete
A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.
| Metric | DeepSeek R1 0528 (May '25) | DeepSeek V3.1 (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 13.1 | 13.5 | +3.1% DeepSeek V3.1 (Reason… is 3.1% more intelligent |
| Total AA cost (lower is better) | Not reported | Not reported | — not comparable |
| End-to-end time (lower is better) | 76.91s | 23.64s | −69.3% DeepSeek V3.1 (Reason… is 69.3% faster |
| Price per 1M tokens (in / out) | $1.85 / $2.75 | $0.58 / $1.68 | |
| Input modalities | Text | Text |
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-r1/deepseek-v3-1-reasoning · Markdown: /api/v1/compare/deepseek-r1/deepseek-v3-1-reasoning?format=md · llms.txt · agent skill